Beat reclassification

This application claims priority to Provisional Application No. 63/335,621, filed Apr. 27, 2022, all of which are herein incorporated by reference in their entirety.

The present disclosure relates to devices, methods, and systems for analyzing cardiac activity and cardiac events.

Monitoring devices for collecting biometric data are becoming increasingly common in diagnosing and treating medical conditions in patients. For example, mobile devices can be used to monitor cardiac data in a patient. This cardiac monitoring can empower physicians with valuable information regarding the occurrence and regularity of a variety of heart conditions and irregularities in patients. Cardiac monitoring can be used, for example, to identify abnormal cardiac rhythms, so that critical alerts can be provided to patients, physicians, or other care providers and patients can be treated.

In Example 1, a method includes receiving, by a first computing system, electrocardiogram (ECG) data and metadata associated with the ECG data. The metadata includes an initial cardiac event classification and an initial beat classification for beats occurring during a first event associated with the initial cardiac event classification. The method further includes displaying the ECG data in a user interface, receiving a command to change the initial cardiac event classification to a subsequent cardiac event classification, and automatically modifying the initial beat classifications to subsequent beat classifications based on the subsequent cardiac event classification.

In Example 2, the method of Example 1, wherein the initial cardiac event classification is an atrial fibrillation event, a normal sinus event, or a ventricular tachycardia event, wherein the subsequent cardiac event classification is a supraventricular event, wherein the subsequent beat classifications are supraventricular beats.

In Example 3, the method of Example 1, wherein the initial cardiac event classification is an atrial fibrillation event, a normal sinus event, or a supraventricular event, wherein the subsequent cardiac event classification is a ventricular tachycardia event, wherein the subsequent beat classifications are ventricular beats.

In Example 4, the method of Example 1, wherein the initial cardiac event classification is a ventricular tachycardia event or a supraventricular event, wherein the subsequent cardiac event classification is a normal sinus event, wherein the subsequent beat classifications are normal beats.

In Example 5, the method of Example 1, wherein the initial cardiac event classification is a ventricular tachycardia event or a supraventricular event, wherein the subsequent cardiac event classification is an atrial fibrillation event, wherein the subsequent beat classifications are normal beats.

In Example 6, the method of any of the preceding Examples, wherein the initial beat classifications include a first beat type and a second beat type, wherein the automatically modifying the initial beat classifications to the subsequent beat classifications includes modifying only the first beat type.

In Example 7, the method of any of the preceding Examples, further including displaying, in the UI, the initial beat classifications and the initial cardiac event classification and, after the automatically modifying step, displaying the subsequent beat classifications and the subsequent cardiac event classification.

In Example 8, the method of any of the preceding Examples, wherein the initial beat classifications and the initial cardiac event classification are determined by a deep learning neural network operated by a server, wherein the subsequent beat classifications are determined by the first computing system.

In Example 9, the method of Example 8, wherein the subsequent beat classifications are determined by executing computer code by a web browser operating on the first computing system.

In Example 10, the method of Example 8, further including receiving, by the first computing system, the computer code in a data package that also includes the ECG data and the metadata.

In Example 11, the method of any of the preceding Examples, wherein the command is generated in response to receiving input, via the UI, from a user.

In Example 12, the method of any of the preceding Examples, further including receiving, by the first computing system, a second set of ECG data and a second set of metadata associated with the second set of ECG data. The second set of metadata includes a first cardiac event classification and a first beat classification for each beat occurring during a second event associated with the first cardiac event classification. The method further includes receiving a first command to change the first cardiac event classification to a second cardiac event classification and maintaining the first beat classifications to second beat classifications based on the second cardiac event classification.

In Example 13, a computer program product including instructions to cause one or more processors to carry out the steps of the method of Examples 1-12.

In Example 14, a computer-readable medium having stored thereon the computer program product of Example 13.

In Example 15, a computer including the computer-readable medium of Example 14.

In Example 16, a system includes a remote computing system with a UI, a first processor, and a first computer-readable medium having a first set of computer-executable instructions embodied thereon. The first set of instructions configured to be executed by the first processor to cause the first processor to: display the ECG data in the UI after receiving ECG data and metadata. The metadata including an initial cardiac event classification and an initial beat classification for beats occurring during a first event associated with the initial cardiac event classification. The first set of instructions are further configured to receive a command to change the initial cardiac event classification to a subsequent cardiac event classification and automatically modify the initial beat classifications to subsequent beat classifications based on the subsequent cardiac event classification.

In Example 17, the system of Example 16, wherein the command is generated in response to receiving input, via the UI, from a user.

In Example 18, the system of Example 16, wherein the initial cardiac event classification is an atrial fibrillation event, a normal sinus event, or a supraventricular event, wherein the subsequent cardiac event classification is a ventricular tachycardia event, wherein the subsequent beat classifications are ventricular beats.

In Example 19, the system of Example 16, wherein the initial cardiac event classification is an atrial fibrillation event, a normal sinus event, or a supraventricular event, wherein the subsequent cardiac event classification is a ventricular tachycardia event, wherein the subsequent beat classifications are ventricular beats.

In Example 20, the system of Example 16, wherein the initial cardiac event classification is a ventricular tachycardia event or a supraventricular event, wherein the subsequent cardiac event classification is a normal sinus event, wherein the subsequent beat classifications are normal beats.

In Example 21, the system of Example 16, wherein the initial cardiac event classification is a ventricular tachycardia event or a supraventricular event, wherein the subsequent cardiac event classification is an atrial fibrillation event, wherein the subsequent beat classifications are normal beats.

In Example 22, the system of Example 16, wherein the initial beat classifications include a first beat type and a second beat type, wherein the automatically modifying the initial beat classifications to the subsequent beat classifications includes modifying only the first beat type.

In Example 23, the system of Example 16, wherein the first set of instructions are configured to be executed by the first processor to cause the first processor to: display, in the UI, the initial beat classifications and the initial cardiac event classification and, after the automatically modifying step, display the subsequent beat classifications and the subsequent cardiac event classification.

In Example 24, the system of Example 16, wherein the first set of instructions are configured to be executed via a web browser at the remote computing system.

In Example 25, the system of Example 16, further including a server with a database, a second processor, and a second computer-readable medium having a second set of computer-executable instructions embodied thereon. The second set of instructions are configured to be executed by the second processor to cause the second processor to: determine, using a machine learning model operated by the server and based on ECG data, the initial cardiac event classification and the initial beat classifications. The instructions are further configured to cause the second processor to: store the initial cardiac event classification and initial beat classifications in the database; transmit, to the remote computing system, strips of the initial ECG data, the initial cardiac event classification, the initial beat classifications, and the first set of instructions; receive, from the remote computing system, the subsequent cardiac event classification and the subsequent beat classifications; and replace, in the database, the initial cardiac event classification with the subsequent cardiac event classification and the initial beat classifications with the subsequent beat classifications.

In Example 26, the system of Example 25, wherein the first set of instructions are executed by a web browser at the remote computing system.

In Example 27, a method includes receiving, by a first computing system, ECG data and metadata associated with the ECG data. The metadata includes an initial cardiac event classification and an initial beat classification for beats occurring during a first event associated with the initial cardiac event classification. The method further includes displaying the ECG data in a UI, receiving a command to change the initial cardiac event classification to a subsequent cardiac event classification, and automatically modifying the initial beat classifications to subsequent beat classifications based on the subsequent cardiac event classification.

In Example 28, the method of Example 27, wherein the initial cardiac event classification is an atrial fibrillation event, a normal sinus event, or a supraventricular event, wherein the subsequent cardiac event classification is a ventricular tachycardia event, wherein the subsequent beat classifications are ventricular beats.

In Example 29, the method of Example 27, wherein the initial cardiac event classification is an atrial fibrillation event, a normal sinus event, or a supraventricular event, wherein the subsequent cardiac event classification is a ventricular tachycardia event, wherein the subsequent beat classifications are ventricular beats.

In Example 30, the method of Example 27, wherein the initial cardiac event classification is a ventricular tachycardia event or a supraventricular event, wherein the subsequent cardiac event classification is a normal sinus event, wherein the subsequent beat classifications are normal beats.

In Example 31, the method of Example 27, wherein the initial cardiac event classification is a ventricular tachycardia event or a supraventricular event, wherein the subsequent cardiac event classification is an atrial fibrillation event, wherein the subsequent beat classifications are normal beats.

In Example 32, the method of Example 27, wherein the initial beat classifications include a first beat type and a second beat type, wherein the automatically modifying the initial beat classifications to the subsequent beat classifications comprises modifying only the first beat type.

In Example 33, the method of Example 27, wherein the subsequent beat classifications are determined by executing computer code by a web browser operating on the first computing system.

In Example 34, a method includes determining—using a machine learning model operated by a server and based on ECG data—an initial cardiac event classification and initial beat classifications for beats occurring during an event. The method further includes storing the initial cardiac event classification and initial beat classifications in a database of the server. The method further includes transmitting—to a remote computing system—strips of the initial ECG data, the initial cardiac event classification, the initial beat classifications, and executable code. The method further includes receiving, from the remote computing system, a subsequent cardiac event classification and subsequent beat classifications and replacing, in the database, the initial cardiac event classification with the subsequent cardiac event classification and the initial beat classifications with the subsequent beat classifications.

In Example 35, the method of Example 34, further including training the machine learning model with the subsequent cardiac event classification and the subsequent beat classifications.

While multiple instances are disclosed, still other instances of the present disclosure will become apparent to those skilled in the art from the following detailed description, which shows and describes illustrative instances of the disclosure. Accordingly, the drawings and detailed description are to be regarded as illustrative in nature and not restrictive.

While the disclosed subject matter is amenable to various modifications and alternative forms, specific instances have been shown by way of example in the drawings and are described in detail below. The intention, however, is not to limit the disclosure to the particular instances described. On the contrary, the disclosure is intended to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure as defined by the appended claims.

The present disclosure relates to devices, methods, and systems for facilitating analysis of cardiac activity and cardiac events (e.g., abnormal cardiac rhythms or other issues).

Electrocardiogram (ECG) data of a patient can be used to identify whether the patient has experienced a cardiac event and what type of cardiac event occurred. One input to determining the type of cardiac event includes the types (or classifications) of heartbeats experienced during the cardiac event. As such, an ECG analysis system may automatically determine that a certain type of cardiac event occurred based on—among other things—how the system classified the beats that occurred during the event. However, if the beats were initially misclassified, the determined type of cardiac event may also be misclassified. The cardiac event may then need to be reclassified. It follows, then, that the underlying beats may also need to be reclassified. Instances of the present disclosure are accordingly directed to systems, methods, and devices for facilitating reclassification of ECG data.

illustrates a patientand an example system. The systemincludes a monitorattached to the patientto detect cardiac activity of the patient. The monitormay produce electric signals that represent the cardiac activity in the patient. For example, the monitormay detect the patient's heart beating (e.g., using infrared sensors, electrodes) and convert the detected heartbeat into electric signals representing ECG data. The monitorcommunicates the ECG data to a mobile device(e.g., a mobile phone).

The mobile devicemay include a program (e.g., mobile phone application) that receives, processes, and analyzes the ECG data. For example, the program may analyze the ECG data and detect or flag cardiac events (e.g., periods of irregular cardiac activity) contained within the ECG data. As noted above, because ECG data may be getting continuously generated, the amount of ECG data can be overwhelming to store and process locally on the mobile device. As such, the mobile devicecan periodically transmit chunks of the ECG data to another device or system, which can process, append together, and archive the chunks of the ECG data and metadata (e.g., time, duration, detected/flagged cardiac events) associated with the chunks of ECG data. In certain instances, the monitormay be programmed to transmit the ECG data directly to the other device or system without utilizing the mobile device. Also, in certain instances, the monitorand/or the mobile deviceincludes a button or touch-screen icon that allows the patientto initiate an event. Such an indication can be recorded and communicated to the other device or system. In other instances involving multi-day studies, the ECG data and associated metadata are transmitted in larger chunks.

Cardiac Event Server

In the example shown in, the mobile devicetransmits the ECG data (and associated metadata, if any) to a cardiac event server(hereinafter “the server” for brevity). The serverincludes multiple platforms, layers, or modules that work together to process and analyze the ECG data such that cardiac events can be detected, filtered, prioritized, and ultimately reported to a patient's physician for analysis and treatment. In the example of, the serverincludes one or more machine learning models(e.g., types of deep neural networks), a cardiac event router, a report platform, and a notification platform. Although only one serveris shown in, the servercan include multiple separate physical servers, and the various platforms/modules/layers can be distributed among the multiple servers. Each of the platforms/modules/layers can represent separate programs, applications, and/or blocks of code where the output of one of the platforms/modules/layers is an input to another of the platforms/modules/layers. Each platform/module/layer can use application programming interfaces to communicate between or among the other platforms/modules/layers as well as systems and devices external to the server.

The serverapplies the machine learning modelto the ECG data to classify cardiac activity of the patient. For example, the machine learning modelmay compare the ECG data to labeled ECG data to determine which labeled ECG data the ECG data most closely resembles. The labeled ECG data may identify a particular cardiac event, including but not limited to ventricular tachycardia, bradycardia, atrial fibrillation, pause, normal sinus rhythm, or artifact/noise. Further, the labeled ECG data may identify beat classifications such as normal, ventricular, and supraventricular.

In certain embodiments, the machine learning modelincludes two paths, where the first path is a deep convolutional neural network and the second path is a deep fully-connected neural network. The deep convolutional neural network receives one or more sets of beats (e.g., beat trains with 3-10 beats) which are processed through a series of layers in the deep convolutional neural network. The series of layers can include a convolution layer to perform convolution on time series data in the beat trains, a batch normalization layer to normalize the output from the convolution layer (e.g., centering the results around an origin), and a non-linear activation function layer to receive the normalized values from the batch normalization layer. The beat trains then pass through a repeating set of layers such as another convolution layer, a batch normalization layer, a non-linear activation function layer. This set of layers can be repeated multiple times.

The deep fully connected neural network receives RR-interval data (e.g., time intervals between adjacent beats) and processes the RR-interval data through a series of layers: a fully connected layer, a non-linear activation function layer, another fully connected layer, another non-linear activation function layer, and a regularization layer. The output from the two paths is then provided to the fully connected layer. The resulting values are passed through a fully connected layer and a softmax layer to produce probability distributions for the classes of beats.

If the machine learning modeldetermines that the ECG data most closely resembles a labeled ECG data associated with a cardiac event, then the machine learning modelmay determine that the patienthas experienced that cardiac event. Additionally, the machine learning modelmay measure or determine certain characteristics of the cardiac activity of the patientbased on the ECG data. For example, the machine learning modelmay determine a heart rate, a duration, or a beat count of the patientduring the cardiac event based on the ECG data. The serverstores the cardiac event (and associated metadata such as information like beat classification, heart rate, duration, beat count, etc.) in a database for storage. Subsequently, the servermay retrieve the cardiac event and associated information from the database.